超越局部编辑：基于嵌入的虚拟化知识用于更广泛的评估和保护模型编辑
Beyond Local Edits: Embedding-Virtualized Knowledge for Broader Evaluation and Preservation of Model Editing
AI总结：
本文提出嵌入虚拟化知识（EVK）方法，通过嵌入空间中的可控扰动扩展知识区域，构建EVK-Bench评估基准，并提出EVK-Align模块以提升知识保留与编辑准确性。
摘要：
大型语言模型的知识编辑方法通常通过预定义基准评估，但这些评估受限于有限的数据样本，无法全面反映编辑对模型知识系统的影响。本文引入嵌入虚拟化知识（EVK），通过嵌入空间中的可控扰动扩展知识区域，构建EVK-Bench评估基准，量化编辑引起的潜在知识漂移，并提出EVK-Align模块以约束嵌入层面的知识漂移，实验表明该方法能更全面地评估并显著提升知识保留，而不影响编辑准确性。
英文摘要：
Knowledge editing methods for large language models are commonly evaluated using predefined benchmarks that assess edited facts together with a limited set of related or neighboring knowledge. While effective, such evaluations remain confined to finite, dataset-bounded samples, leaving the broader impact of editing on the model's knowledge system insufficiently understood. To address this gap, we introduce Embedding-Virtualized Knowledge (EVK) that characterizes model knowledge through controlled perturbations in embedding space, enabling the exploration of a substantially broader and virtualized knowledge region beyond explicit data annotations. Based on EVK, we construct an embedding-level evaluation benchmark EVK-Bench that quantifies potential knowledge drift induced by editing, revealing effects that are not captured by conventional sample-based metrics. Furthermore, we propose a plug-and-play EVK-Align module that constrains embedding-level knowledge drift during editing and can be seamlessly integrated into existing editing methods. Experiments demonstrate that our approach enables more comprehensive evaluation while significantly improving knowledge preservation without sacrificing editing accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
